Zahra Gholami's repositories
Awesome-Semi-Supervised-Semantic-Segmentation
A summary of recent semi-supervised semantic segmentation methods
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
EchoGraphs
[MICCAI 2022] The official repository of Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound. Project page: https://guybenyosef.github.io/EchoGraphs/
Efficient-AI-Backbones
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
FastFlowNet
FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation (ICRA 2021)
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
mmselfsup
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
motion-transformer
A Spatio-temporal Transformer for 3D Human Motion Prediction
neurite
Neural networks toolbox focused on medical image analysis
ProPainter
[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting
SAM-Med2D
Official implementation of SAM-Med2D
sam-pt
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
segmentation_models.pytorch
Segmentation models with pretrained backbones. PyTorch.
semi_seg_proto
Official implementation of "Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization" (NeurIPS2022)
SETR
[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
SSL_ELN
This repository contains the official implementation of Semi-supervised Semantic Segmentation with Error Localization Network that has been accepted to 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022).
transformer
PyTorch Implementation of "Attention Is All You Need"
UniFormer
[ICLR2022] official implementation of UniFormer
vedo
A python module for scientific analysis of 3D data
VideoMAE
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
vision
Datasets, Transforms and Models specific to Computer Vision
vital
Personal fork of the `vital` library to iterate on new projects before upstreaming them
voxelmorph
Unsupervised Learning for Image Registration
vpt
❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119